Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: the exact columns, that Status is Partiful's label (e.g. Approved on a Guest Approval event), that the text comes back inline rather than as a link, and that ids/emails/phones are excluded. Those are the details an agent needs before trusting the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The key framing (CSV mirroring the Export CSV button) is front-loaded and the rest is dense with concrete facts. The second sentence slightly restates the first's equivalence to the button, a minor redundancy, but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does it fully: inline CSV text, row meaning, suggested filename, and excluded fields. Nothing an agent needs to call or interpret the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented. The description restates status filtering ('for the chosen RSVP statuses') and clarifies the meaning of status labels as they appear in the output, but adds little syntax or semantics about the parameters themselves. Baseline 3 fits.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb+resource+format: 'The guest list as CSV, the same file as the Export CSV button.' It also names the sibling it is not (list_guests for guest ids), so an agent can distinguish it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear routing rule away from the sibling: 'for guest ids use list_guests' and states the audience constraint ('Hosts only'). It implies filtering via the chosen RSVP statuses but never explicitly frames when to prefer this over list_guests for a plain listing, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.